Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 395 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.6319. Min Act: -0.1700

Data Index: 767645 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.3812. Min Act: -0.1700

Data Index: 299810 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.3499. Min Act: -0.1700

Data Index: 1274899 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2871. Min Act: -0.1700

Data Index: 920291 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 811683 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2871. Min Act: -0.1700

Data Index: 406649 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2713. Min Act: -0.1700

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2871. Min Act: -0.1700

Data Index: 746037 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 707972 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2713. Min Act: -0.1700

Data Index: 1169704 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2871. Min Act: -0.1700

Data Index: 334114 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 1106269 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2399. Min Act: -0.1700

Data Index: 178385 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2399. Min Act: -0.1700

Data Index: 602515 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 43560 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2399. Min Act: -0.1700

Data Index: 186158 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2399. Min Act: -0.1700

Data Index: 618382 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2399. Min Act: -0.1700

Data Index: 200855 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.6319. Min Range: -3.6319

Max Act: 3.2556. Min Act: -0.1700

Data Index: 1258644 (C4 (Web Text))

Max Activating Token Index: 541